Discrete wavelet and neural network for transmission line fault classification

This paper presents an efficient wavelet and neural network (WNN) based algorithm for fault classification in single circuit transmission line. The first level discrete wavelet transform is applied to decompose the post fault current signals of the transmission line into a series of coefficient components (approximation and detail). The values of the approximation coefficients obtained can accurately discriminate between all types of fault in transmission line and reduce the number of data feeding to the ANN. These coefficients are further used to train an Artificial Neural Network (ANN) fitting function. The trained FFNN clearly distinguishes and classify very accurate and very fast the fault type. A typical generation system connected by single circuit transmission line to many nodes of lodes at the receiving end was simulated using MATLAB simulation software using only one node to do this work. The generated data were used by the MATLAB software to test the performance of the proposed technique. The simulation results obtained show that the new algorithm is more reliable and accurate.